Amrata Yadav

AmrataYadav

AI & ML interests

NLP, LLM

Recent Activity

updated a model 18 days ago

AmrataYadav/Qwen2.5-3B-Custom-SFT

published a model 18 days ago

AmrataYadav/Qwen2.5-3B-Custom-SFT

updated a Space 18 days ago

AmrataYadav/trackio

View all activity

Organizations

None yet

upvoted an article about 1 month ago

Article

We Got Claude to Fine-Tune an Open Source LLM

Dec 4, 2025

•

591

upvoted an article 10 months ago

Article

Hyperparameter Search with Transformers and Ray Tune

Nov 2, 2020

•

upvoted a collection 11 months ago

IndicTrans2

Collection

Models(En-Indic, Indic-En, Indic-Indic) in 2 variants (base and dist) and Benchmarks (IN22-Gen and IN22-Conv) released as a part of IndicTrans2. • 10 items • Updated Sep 5, 2025 • 24

upvoted 3 articles 11 months ago

Article

Investing in Performance: Fine-tune small models with LLM insights - a CFM case study

Dec 3, 2024

•

Article

Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA

May 24, 2023

•

173

Article

Fine-tuning 20B LLMs with RLHF on a 24GB consumer GPU

Mar 9, 2023

•

upvoted an article about 1 year ago

Article

Llama 3.1 - 405B, 70B & 8B with multilinguality and long context

Jul 23, 2024

•

241

Amrata Yadav

AI & ML interests

Recent Activity

Organizations

AmrataYadav's activity

We Got Claude to Fine-Tune an Open Source LLM

Hyperparameter Search with Transformers and Ray Tune

Investing in Performance: Fine-tune small models with LLM insights - a CFM case study

Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA

Fine-tuning 20B LLMs with RLHF on a 24GB consumer GPU

Llama 3.1 - 405B, 70B & 8B with multilinguality and long context